© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 7748
    Prev
    Next
    INDEX
    Explanations

    references to artistic representations and critiques of society

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    after "stories" or "which"

    np_acts-logits-general · gemini-2.0-flash

    stories blur and tear

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LookAnd
    -0.66
     fancies
    -0.61
     ruining
    -0.60
    ็จ
    -0.60
     annoys
    -0.58
     hates
    -0.58
     étoit
    -0.57
     upvoted
    -0.57
     buoni
    -0.56
     ruined
    -0.56
    POSITIVE LOGITS
     challenge
    0.80
     reflect
    0.78
     desafi
    0.74
     reveal
    0.74
     interro
    0.74
    reflect
    0.72
     weaving
    0.71
     illum
    0.70
    reveal
    0.69
     interrog
    0.69
    Activations Density 0.320%

    No Known Activations